Characterization of Infants’ General Movements Using a Commercial RGB-Depth Sensor and a Deep Neural Network Tracking Processing Tool: An Exploratory Study

Abstract

Cerebral palsy, the most common childhood neuromotor disorder, is often diagnosed through visual assessment of general movements (GM) in infancy. This skill requires extensive training and is thus difficult to implement on a large scale. Automated analysis of GM performed using low-cost instrumentation in the home may be used to estimate quantitative metrics predictive of movement disorders. This study explored if infants’ GM may be successfully evaluated in a familiar environment by processing the 3D trajectories of points of interest (PoI) obtained from recordings of a single commercial RGB-D sensor. The RGB videos were processed using an open-source markerless motion tracking method which allowed the estimation of the 2D trajectories of the selected PoI and a purposely developed method which allowed the reconstruction of their 3D trajectories making use of the data recorded with the depth sensor. Eight infants’ GM were recorded in the home at 3, 4, and 5 months of age. Eight GM metrics proposed in the literature in addition to a novel metric were estimated from the PoI trajectories at each timepoint. A pediatric neurologist and physiatrist provided an overall clinical evaluation from infants’ video. Subsequently, a comparison between metrics and clinical evaluation was performed. The results demonstrated that GM metrics may be meaningfully estimated and potentially used for early identification of movement disorders.

Current Applications of Artificial Intelligence in the Neonatal Intensive Care Unit

“…The authors concluded that ML models could be useful for healthcare services and enhance the long-term outcomes of preterm neonates. Furthermore, in a recent study, Balta et al proposed an AI-based automated monitoring of newborns' general motions, a crucial screening test for detecting neuromotor problems in children [104]. The authors created an automated model to analyze infants' overall motions, by processing videos taken with a simple camera at home.…”

Evolution of a System to Monitor Infant Neuromotor Development in the Home: Lessons from COVID-19

“…All infants enrolled in the pilot were nominally TD, recruited from the community, with no developmental problems of which parents were aware or communicated. However, study clinicians, specialists in pediatric neurology and physiatry, noted that the presumption of TD was difficult to confirm on video due to infants slipping into positions in the standardized infant seat that made it harder for them to choose to move one arm or the other unimpeded [ 27 ]. This observation mirrored comments from HUGS-1 parents that their babies’ movements, particularly before babies’ trunk control, was well developed, seemed awkward.…”

“…A prime example of what could be considered a failure of coaching was moving the camera during the session. This action resulted in the need to explore approaches to analysis, as stability of the camera was a pillar of the kinematic algorithm developed to analyze spontaneous movements in HUGS-1 [ 27 ]. Other actions that we did not anticipate that added complexity to analysis were bouncing the baby seat during a session and continuing to test on broken toy bars that were suspect, even though they continued to flash colored lights, play music, and vibrate.…”

“…To compare the spontaneous movements of HUGS-2 at-risk infants to those of HUGS-1 TD infants, the average velocity and peak velocity of both right and left elbows and total path lengths of the left and right wrists were calculated for at-risk infants and de novo for TD infants applying a uniform kinematic approach (see Supplement E for the de novo methodology. It applied a different approach than that described in our previously published work [ 27 ] to facilitate comparison of HUGS-2 versus HUGS-1 kinematics). Again, an LLM [ 28 ] was chosen for conducting the analysis with α set at 0.1 in consideration of the small sample size.…”

Novel Multi-View RGB Sensor for Continuous Motion Analysis in Kinetic Chain Exercises: A Pilot Study for Simultaneous Validity and Intra-Test Reliability

“…It is parallel to the ground, separates the upper and lower parts, and is further divided into the superior and inner parts. Rotation typically occurs in this plane [ 6 , 7 , 14 , 15 , 16 ]. To explain human movement, the kinetic chain is divided into an open kinetic chain (OKC) and a closed kinetic chain (CKC).…”